Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.5992. Min Act: -0.1700
Data Index: 1382828 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.5055. Min Act: -0.1700
Data Index: 6497359 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.4742. Min Act: -0.1700
Data Index: 3306679 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.5055. Min Act: -0.1700
Data Index: 5131460 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.4117. Min Act: -0.1700
Data Index: 6461464 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.4117. Min Act: -0.1700
Data Index: 4603414 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.4117. Min Act: -0.1700
Data Index: 2356969 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.3805. Min Act: -0.1700
Data Index: 5618036 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.3180. Min Act: -0.1700
Data Index: 7901429 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.3492. Min Act: -0.1700
Data Index: 6819424 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.3180. Min Act: -0.1700
Data Index: 6122500 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.3492. Min Act: -0.1700
Data Index: 1819019 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.2867. Min Act: -0.1700
Data Index: 4393789 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.2867. Min Act: -0.1700
Data Index: 8256326 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.2555. Min Act: -0.1700
Data Index: 8808591 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.2555. Min Act: -0.1700
Data Index: 4068912 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.2242. Min Act: -0.1700
Data Index: 5543863 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.2242. Min Act: -0.1700
Data Index: 496121 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.1930. Min Act: -0.1700
Data Index: 4772394 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5992. Min Range: -5.5992
Max Act: 5.1930. Min Act: -0.1700
Data Index: 971602 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19